© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57639
    Prev
    Next
    INDEX
    Explanations

    financial results and outlook

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    5
    -0.09
    2
    -0.09
    4
    -0.08
    3
    -0.08
    6
    -0.08
    åıijå±ķ壮大
    -0.08
    9
    -0.08
    coded
    -0.08
    1
    -0.08
    deb
    -0.07
    POSITIVE LOGITS
    ä¸ļ绩
    0.13
    èĤ¡ä»·
    0.12
    æĢ»æĶ¶åħ¥
    0.11
    主èIJ¥ä¸ļåĬ¡
    0.11
    å¿«æĬ¥
    0.11
    æĶ¶åħ¥
    0.11
    åĩĢåĪ©æ¶¦
    0.10
    æ¯ıèĤ¡
    0.10
    æ¯ĽåĪ©çİĩ
    0.10
    èIJ¥æĶ¶
    0.10
    Activations Density 0.035%

    No Known Activations